An adaptive variable frequency speed control method for belt conveyor

Abstract

The present invention provides an adaptive variable frequency speed control method for a belt conveyor, comprising: obtaining current material loading data through a weight sensor, comparing the current material loading data with a preset standard loading, obtaining a deviation value of the loading, controlling the feeding speed of a feeding device according to the size of the deviation value, and maintaining the conveyor loading capacity within a reasonable range by adjusting the material loading speed; obtaining current belt speed data through a speed sensor, comparing the current belt speed data with a preset standard speed, obtaining a speed deviation value, controlling the output frequency of a frequency converter according to the size and positive and negative of the deviation value, and maintaining the belt speed within a reasonable range by adjusting the motor speed. The present invention can automatically optimize the control strategy according to different working conditions, effectively reduce belt tension and speed fluctuations, ensure the stable operation of the conveyor in complex and changing environments, and improve conveying efficiency and safety.

Description

Technical Field

[0001] The invention belongs to the field of belt conveyor control, and in particular relates to an adaptive frequency conversion speed regulation control method for a belt conveyor. Background Art

[0002] During the operation of a belt conveyor, changes in material load and conveying distance cause belt tension and speed to fluctuate. Traditional fixed-speed control methods struggle to adapt to these dynamic changes, easily causing belt slippage and deviation, impacting conveying efficiency and equipment life. Furthermore, due to the complex and ever-changing field environment, the required conveyor belt length must be adjusted in real time based on operating conditions. Achieving adaptive control of conveyor speed and belt length to ensure smooth operation under varying operating conditions is a pressing technical challenge. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes an adaptive variable frequency speed control method for a belt conveyor to solve the problems existing in the above prior art.

[0004] To achieve the above object, the present invention provides an adaptive variable frequency speed control method for a belt conveyor, comprising the following steps:

[0005] Acquire belt tension data, transmit the tension data to a control system to determine whether it exceeds a preset tension threshold range, and if so, adjust the belt tension through a control signal;

[0006] Acquire current conveying distance data, compare the current conveying distance data with a preset standard conveying distance, obtain a conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value;

[0007] Obtaining current material loading data, comparing the current material loading data with a preset standard loading amount to obtain a loading deviation value, and adjusting the material loading speed according to the loading deviation value;

[0008] Acquire current belt speed data, compare the current belt speed data with a preset standard speed to obtain a speed deviation value, and adjust the motor speed according to the speed deviation value;

[0009] The running status of the belt is monitored in real time through machine vision technology to determine whether it is slipping or deviating. If slipping or deviating occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slipping or deviation.

[0010] The control system adopts an adaptive control algorithm to calculate the optimal parameter combination of the PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination.

[0011] Preferably, adjusting the belt tension includes: the control system issues an adjustment instruction, and by adjusting the output frequency and voltage amplitude of the inverter, changes the speed and torque of the motor, thereby adjusting the running speed and tension of the belt.

[0012] Preferably, adjusting the belt length includes: controlling the extension amount and extension direction of the telescopic mechanism to adjust the belt length according to the size and positive and negative of the conveying distance deviation value, thereby compensating for belt tension fluctuations caused by changes in the conveying distance.

[0013] Preferably, adjusting the loading speed of the material includes: controlling the feeding speed of the feeding device according to the size of the loading amount deviation value, and controlling the loading amount by adjusting the loading speed of the material.

[0014] Preferably, adjusting the output of the frequency converter and the tensioning force of the tensioning device according to the degree of slippage and deviation includes:

[0015] Construct a skidding and deviation discrimination model based on support vector machine;

[0016] Acquire the belt surface image, use image preprocessing technology to denoise and enhance the image; use texture feature extraction algorithm to extract the belt surface texture features and obtain the texture feature vector;

[0017] Inputting the texture feature vector into a slip and deviation discrimination model to obtain a belt state;

[0018] The output of the frequency converter and the tensioning force of the tensioning device are adjusted according to the belt state.

[0019] Preferably, regulating the belt conveyor includes:

[0020] The neural network is trained through historical operating data to establish a mapping relationship between conveyor operating conditions and optimal control parameters, and obtain an adaptive control model;

[0021] Calculate the optimal parameter combination of PID controller through adaptive control model;

[0022] The belt conveyor is regulated according to the optimal parameter combination.

[0023] The present invention also provides an adaptive variable frequency speed control system for a belt conveyor, comprising:

[0024] The tension control module is used to obtain the belt tension data and transmit the tension data to the control system to determine whether it exceeds the preset tension threshold range. If it exceeds the preset tension threshold range, the control system adjusts the belt tension through the control signal;

[0025] A conveying distance compensation module is used to obtain current conveying distance data, compare the current conveying distance data with a preset standard conveying distance, obtain a conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value;

[0026] A loading control module is used to obtain current material loading data, compare the current material loading data with a preset standard loading, obtain a loading deviation value, and adjust the material loading speed according to the loading deviation value;

[0027] A speed control module is used to obtain current belt speed data, compare the current belt speed data with a preset standard speed, obtain a speed deviation value, and adjust the motor speed according to the speed deviation value;

[0028] The operating status monitoring module is used to monitor the operating status of the belt in real time through machine vision technology to determine whether slippage or deviation occurs. If slippage or deviation occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slippage or deviation.

[0029] The adaptive control module adopts an adaptive control algorithm to calculate the optimal parameter combination of the PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination.

[0030] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0031] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0032] The present invention also provides a computer program product, comprising a computer program, which implements the steps of the method when executed by a processor.

[0033] Compared with the prior art, the present invention has the following advantages and technical effects:

[0034] The present invention discloses an adaptive variable frequency speed control method for a belt conveyor. Key parameters such as belt tension, conveying distance, material loading and operating speed are monitored in real time by a variety of sensors, and the data is transmitted to the control system for analysis and processing. When it is detected that the parameters deviate from the preset range, the present invention automatically adjusts the inverter output, telescopic mechanism and feeding device, etc. to maintain the stability of the belt tension and speed. At the same time, the present invention adopts machine vision technology to monitor the running status of the belt, identify slippage and deviation phenomena and make timely adjustments. Through the adaptive control algorithm, the present invention can automatically optimize the control strategy according to different working conditions, effectively reduce belt tension and speed fluctuations, ensure the stable operation of the conveyor in complex and changing environments, and improve transportation efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0036] Figure 1 Flowchart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] Example 1

[0040] like Figure 1 As shown, this embodiment provides an adaptive variable frequency speed control method for a belt conveyor, which is characterized by comprising the following steps:

[0041] Acquire belt tension data, transmit the tension data to a control system to determine whether it exceeds a preset tension threshold range, and if so, adjust the belt tension through a control signal;

[0042] Acquire current conveying distance data, compare the current conveying distance data with a preset standard conveying distance, obtain a conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value;

[0043] Obtaining current material loading data, comparing the current material loading data with a preset standard loading amount to obtain a loading deviation value, and adjusting the material loading speed according to the loading deviation value;

[0044] Acquire current belt speed data, compare the current belt speed data with a preset standard speed to obtain a speed deviation value, and adjust the motor speed according to the speed deviation value;

[0045] The running status of the belt is monitored in real time through machine vision technology to determine whether it is slipping or deviating. If slipping or deviating occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slipping or deviation.

[0046] The control system adopts an adaptive control algorithm to calculate the optimal parameter combination of the PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination.

[0047] The specific steps include:

[0048] Step S101, obtain the belt tension data and transmit the tension data to the control system. If the tension data exceeds the preset tension threshold range, the control system issues an adjustment instruction to change the motor speed and torque by adjusting the output frequency and voltage amplitude of the inverter, thereby adjusting the belt running speed and tension to maintain the belt tension within a reasonable range.

[0049] Specifically, the belt tension data is obtained and transmitted to the control system. The control system determines whether the tension data exceeds the preset tension threshold range. If it does, the control system issues an adjustment instruction. According to the adjustment instruction, the speed and torque of the motor are changed by adjusting the output frequency and voltage amplitude of the inverter. The change data of the motor speed and torque are obtained, and the adjustment values of the belt running speed and tension are determined based on the change data. The adjustment value is transmitted to the control system, and the control system controls the belt running speed and tension based on the adjustment value to maintain the belt tension within a reasonable range. A mathematical model between the belt tension and the motor speed and torque is established, and the model is trained using a machine learning algorithm to obtain an optimized adjustment strategy. The optimized adjustment strategy is applied to the control system to achieve adaptive adjustment of the belt tension and improve the stability and reliability of the system.

[0050] In this embodiment, the core of the belt tension control system lies in establishing an accurate mathematical model and optimization strategy. First, historical data must be collected, including belt tension, motor speed, and torque data. For example, on a certain production line, belt tension data collected by a tension sensor ranges from 1,000 to 1,500 Newtons, motor speeds from 600 to 800 rpm, and torques from 50 to 70 Newton-meters. This data forms the basis for model training. A multivariate linear regression algorithm can analyze the relationship between these three variables. For example, when the motor speed increases by 100 rpm, the belt tension increases by 100 Newtons; when the torque increases by 10 Newton-meters, the tension increases by 50 Newtons. This relationship allows for the establishment of a preliminary mathematical model. A support vector machine algorithm can handle nonlinear relationships and improve model accuracy. In practical applications, when the production line speed suddenly increases, the support vector machine algorithm can more accurately predict the required tension adjustment. When converting the optimized adjustment strategy into a control rule, it is necessary to consider the actual operating conditions. For example, on a paper production line, the belt tension should be maintained at approximately 1,200 Newtons during normal operation. When tension exceeds 1,300 Newtons, the control system automatically reduces the motor speed by 20 revolutions per minute. When tension falls below 1,100 Newtons, the torque is increased by 5 Newton-meters. As the control system collects data and makes adjustments in real time, it needs to record the effects of these adjustments. For example, it records the tension trend after each adjustment, the adjustment time, and whether oscillation occurs. This data is used for subsequent model optimization. In a steel production line application, analysis revealed that the effectiveness of the same adjustment parameters decreases during high summer temperatures, necessitating increased adjustments. Regular model retraining should be based on actual production practices. For example, monthly model validation for a conveyor belt system revealed that the relationship between tension and speed changes with belt age, necessitating timely adjustments to model parameters. This ensures that the control strategy remains optimal and adapts to varying operating conditions. This adaptive adjustment significantly improves system stability, reduces downtime due to tension anomalies, and increases production efficiency.

[0051] In step S102, a laser ranging sensor is used to obtain current conveying distance data, and the current conveying distance data is compared with a preset standard conveying distance to obtain a conveying distance deviation value. According to the size and positive / negative sign of the deviation value, the telescopic amount and direction of the telescopic mechanism are controlled, and the belt tension fluctuation caused by the change in conveying distance is compensated by adjusting the length of the belt.

[0052] Specifically, the current conveying distance data collected by the laser ranging sensor is obtained; the current conveying distance data is compared with the preset standard conveying distance to obtain a distance deviation value; the positive or negative sign of the distance deviation value is determined, if it is positive, it indicates that the current conveying distance is greater than the standard distance, and if it is negative, it indicates that the current conveying distance is less than the standard distance; according to the size of the distance deviation value, the extension and contraction amount of the telescopic mechanism is determined, and the larger the deviation value, the larger the extension and contraction amount; according to the positive or negative sign of the distance deviation value, the extension and contraction direction of the telescopic mechanism is determined, if the deviation is positive, the extension and contraction direction is the direction of shortening the belt, and if the deviation is negative, the extension and contraction direction is the direction of extending the belt; the telescopic mechanism is controlled to perform telescopic movement according to the determined extension and contraction amount and direction, and the belt tension fluctuation caused by the change in the conveying distance is compensated by adjusting the length of the belt; according to the adjusted belt length, the current conveying distance data is re-acquired, the execution is cyclical, and the belt tension fluctuation is dynamically compensated in real time until the distance deviation value is less than the preset deviation threshold.

[0053] In this embodiment, a laser ranging sensor measures the actual conveying distance of a belt conveyor by emitting a laser beam and receiving the reflected signal, achieving millimeter-level accuracy. For example, a belt conveyor conveying ore has a preset standard conveying distance of 100 meters. The laser ranging sensor measures the current conveying distance as 102 meters. In this case, the distance deviation is +2 meters, indicating that the actual conveying distance exceeds the standard distance. The sign of the distance deviation directly determines the movement direction of the telescopic mechanism. When the deviation is positive, the belt length needs to be shortened, and the telescopic mechanism retracts inward; when the deviation is negative, the belt length needs to be extended, and the telescopic mechanism extends outward. In the example above, with a positive deviation of 2 meters, the telescopic mechanism retracts inward to shorten the belt length. The amount of telescopic movement is positively correlated with the deviation. In practice, a proportional coefficient can be used for conversion, such as setting the telescopic distance to 0.8 times the deviation value. For a 2-meter deviation, the calculated telescopic distance is 1.6 meters. This proportional relationship can be adjusted according to actual operating conditions to ensure effective compensation. The telescopic mechanism is implemented using an electric push rod or hydraulic cylinder, and its movement accuracy directly affects the compensation effect. For example, when an electric actuator receives a command to retract 1.6 meters inward, it uses an internal displacement sensor to provide real-time position feedback, ensuring precise movement. By adjusting the belt length, it effectively compensates for tension fluctuations caused by changes in conveying distance. The compensation process utilizes closed-loop control. After completing one adjustment, the system recollects conveying distance data and calculates a new deviation value. For example, if the adjusted distance is 100.3 meters, the new deviation value is +0.3 meters. If the preset deviation threshold is 0.5 meters, the current deviation is within the allowable range, and the compensation process ends. If it still exceeds the threshold, compensation adjustments continue. This dynamic compensation method responds to changes in conveying distance in real time, maintaining belt tension stability by precisely controlling the movement of the retracting mechanism. In practice, the system automatically adjusts compensation parameters based on different operating conditions. For example, when conveying heavy loads, it can appropriately increase the retraction to ensure effective compensation. Through continuous monitoring and adjustment, belt slack or overtightening is effectively avoided, extending the service life of the equipment.

[0054] In step S103, the current material loading data is obtained through the weight sensor, and the current material loading data is compared with the preset standard loading to obtain a deviation value of the loading. According to the size of the deviation value, the feeding speed of the feeding device is controlled, and the loading speed of the material is adjusted to maintain the loading capacity of the conveyor within a reasonable range.

[0055] Specifically, the material loading data collected by the weight sensor in real time is obtained and used as the current loading data. The standard loading data is read from the preset parameters and used as the target value for optimization control. The difference between the current loading data and the standard loading data is calculated to obtain the loading deviation value. The positive or negative value of the loading deviation value is determined. If it is a positive value, it means that the current loading exceeds the standard loading and the feeding speed needs to be reduced; if it is a negative value, it means that the current loading is lower than the standard loading and the feeding speed needs to be increased. According to the size of the loading deviation value, the proportional-integral-differential (PID) control algorithm is used to calculate the feeding speed adjustment value of the feeding device. The feeding speed adjustment value is transmitted to the control unit of the feeding device to adjust the actual feeding speed of the feeding device, thereby changing the loading speed of the conveyor. After adjusting the feeding speed, the real-time data of the weight sensor is continued to be obtained to realize real-time closed-loop control of the conveyor loading so that it is always maintained within a reasonable range.

[0056] In this embodiment, weight sensors collect load data, which is essential for achieving precise control. For example, using a belt conveyor to transport coal, the sensor measures the deformation of the coal on the belt and converts it into an electrical signal, enabling real-time monitoring. The standard load setting must take into account the conveyor's carrying capacity and operating efficiency. For example, the standard load for a certain belt conveyor model is 100 kilograms of coal per meter of belt. Calculating the load deviation is crucial for subsequent control. If the sensor detects an actual load of 120 kilograms per meter, the deviation from the standard is +20 kilograms, indicating an overload. If the sensor detects 80 kilograms per meter, the deviation is -20 kilograms, indicating an underload. This deviation directly impacts conveying efficiency and equipment life. Feed rate regulation utilizes a proportional-integral-derivative control algorithm, enabling fast response and stable control. The proportional term performs basic adjustments based on the deviation. For example, if the deviation is +20 kilograms, the feed rate can be reduced by 15%. The integral term accumulates historical deviations to eliminate steady-state errors. The differential term predicts the trend of the deviation, improving control sensitivity. In a cement production line, the feeding device may be a screw feeder, whose speed directly affects the load capacity. If the load capacity is detected to be persistently high, the control system will gradually reduce the screw feeder speed until the load capacity returns to the standard value. This process is a continuous closed-loop control process, with data collected and compared after each adjustment. In ore conveying systems, the impact of material particle size on the load capacity must also be considered. Larger ore particles can cause large instantaneous load capacity fluctuations. In this case, smooth control can be achieved by adjusting the sensitivity of the control parameters. For example, setting the sampling period to five seconds can achieve a smoother control response. In practical applications, load capacity control also needs to consider the dynamic characteristics of the conveyor during startup and shutdown. During the initial startup, the feed rate should be increased gradually to avoid sudden loading and shock to the equipment. Similarly, the feed rate should be gradually reduced before shutdown to ensure a smooth transition in material transportation. This dynamic control strategy can effectively extend equipment life and improve operational reliability.

[0057] In step S104, a speed sensor is used to obtain the current belt speed data, and the current belt speed data is compared with a preset standard speed to obtain a speed deviation value. According to the size and positive and negative sign of the deviation value, the output frequency of the inverter is controlled, and the belt speed is maintained within a reasonable range by adjusting the motor speed.

[0058] Specifically, a speed sensor acquires real-time data on the belt's current speed and transmits it to a central control unit. The central control unit compares the current belt speed with a preset standard speed and calculates the deviation between the two. The calculated speed deviation is then checked for sign: a positive deviation indicates the belt speed is above the standard; a negative deviation indicates it is below the standard. Based on the speed deviation, a fuzzy control algorithm is used to determine the adjustment range for the inverter's output frequency. A larger deviation increases the adjustment range. The determined inverter output frequency adjustment value is then transmitted to the inverter, which adjusts the motor speed by changing its output frequency. This change in motor speed drives a corresponding adjustment in the belt speed until the belt speed returns to a reasonable range. By continuously performing these steps, the belt speed is automatically controlled and stabilized near the preset standard speed through real-time data acquisition from the speed sensor and dynamic adjustment of the inverter's output frequency.

[0059] In this embodiment, the speed sensor, typically a photoelectric encoder or Hall effect sensor, is installed at the driven pulley shaft end of the belt conveyor. It detects shaft rotation to determine belt speed. Taking a photoelectric encoder as an example, if the encoder outputs a certain number of pulse signals per revolution, assuming an encoder resolution of 1000 pulses per revolution and a driven pulley diameter of 500 mm, the actual belt speed can be calculated from the pulse frequency. The central control unit processes and analyzes the received speed data. For example, if the standard operating speed of a mining conveyor is set at 2 meters per second and the actual speed is detected at 2.3 meters per second, the calculated speed deviation is positive 0.3 meters per second, indicating that the belt is running too fast and needs to be slowed down. Conversely, if the actual speed is 1.8 meters per second and the deviation is negative 0.3 meters per second, the speed needs to be increased. The fuzzy control algorithm categorizes speed deviation values into different levels: a deviation of less than 0.1 meters per second is considered small, 0.1 to 0.3 meters per second is considered medium, and greater than 0.3 meters per second is considered large. Correspondingly, the frequency converter's output frequency adjustment range is categorized into small, medium, and large adjustments. Taking the standard frequency of 50 Hz as an example, the adjustment range for small deviations is within 1 Hz, for medium deviations it's 2 to 3 Hz, and for large deviations it's 3 Hz or more. The frequency converter controls the motor speed, which in turn affects the belt speed, by varying the output frequency. For example, if the motor's rated speed is 1450 rpm, this corresponds to an output frequency of 50 Hz. When the belt overspeed is detected, the controller issues a frequency reduction command, for example, to 48 Hz, which reduces the motor speed to approximately 1392 rpm, and the belt speed decreases accordingly. This speed regulation method responds quickly and ensures smooth transitions. Through continuous speed detection and frequency adjustment, closed-loop control is established. For example, in a cement plant conveyor, during continuous operation, varying material loads may cause speed fluctuations. The system automatically compensates for these fluctuations. If the speed decreases when loaded with heavier materials, the controller increases the frequency appropriately. As the load decreases, the frequency is reduced accordingly, maintaining a stable speed near the standard value, improving conveying efficiency and equipment life. This automatic control method based on speed feedback effectively avoids the lag and subjectivity of manual operation, ensuring the belt always maintains optimal operating conditions. In actual application, control parameters can be flexibly set according to different working conditions. For example, when conveying fragile materials, a smaller adjustment step size can be used to ensure a smooth transition; when conveying bulk materials, a larger step size can be used to improve adjustment efficiency.

[0060] In step S105, machine vision technology is used to monitor the running status of the belt in real time. The texture features of the belt surface are identified through image processing algorithms to determine whether slipping and deviation occur. If slipping or deviation is detected, the control system will issue an alarm signal. At the same time, according to the degree of slipping and deviation, the output of the inverter and the tensioning force of the tensioning device are adjusted to restore the belt to normal operating state.

[0061] Specifically, an image of the belt surface is acquired, and image preprocessing technology is used to denoise and enhance the image to improve image quality. The texture features of the belt surface are extracted using a texture feature extraction algorithm to obtain a texture feature vector. Based on the pre-established slip and deviation discrimination model, it is determined whether the current belt operation state is slipping or deviating. If slippage is detected, the control system adjusts the inverter output frequency and voltage according to the degree of slippage, changes the motor speed and torque, and restores the belt to normal operation. If deviation is detected, the control system adjusts the tensioning force of the tensioning device according to the degree of deviation to restore the belt to a centered operation state. During the adjustment process, the belt surface image is continuously acquired, the belt operation state is monitored in real time, and it is determined whether the belt has resumed normal operation. If the belt has not resumed normal operation within the preset time, the control system will issue an alarm signal, prompting manual inspection and maintenance.

[0062] In this embodiment, real-time monitoring of the belt's operating status is crucial for ensuring stable production line operation. Belt surface images are acquired using machine vision technology. Image preprocessing techniques, such as denoising and enhancement, significantly improve image quality, laying the foundation for subsequent texture feature extraction. During the texture feature extraction phase, algorithms such as Gabor filters are employed to effectively extract the belt's surface texture features and generate texture feature vectors. These vectors contain subtle structural information about the belt's surface, such as its thickness and direction. For example, a properly functioning belt has a uniform and consistent texture, while slipping creates a blurred and distorted texture, and deviation creates a shifted texture direction. Based on pre-established models for discriminating between slip and deviation, the extracted texture feature vectors are classified using a support vector machine (SVM) or neural network algorithm. If the model output indicates slippage, the system further assesses the degree of slip. For example, mild slip may manifest as only a slight blurring of the texture, while severe slip may result in noticeable texture disturbance. In response to detected slip, the control system determines the motor speed and torque parameters that need to be adjusted according to a pre-set control strategy. For example, in the case of mild slip, the system is set to increase motor speed by 5% and torque by 10%. In the case of severe slip, the speed is increased by 10% and torque by 20%. These parameters are determined based on extensive experimental data and empirical formulas, aiming to quickly restore normal belt operation through small adjustments. Based on these parameters, the control system generates corresponding inverter control instructions. For example, the instructions may include a target frequency of 50Hz and a voltage of 380V. These instructions are sent to the inverter via a communication interface. Upon receiving the instructions, the inverter adjusts its output frequency and voltage, thereby changing the motor speed and torque. The increased motor speed and torque effectively overcome slip and restore stable belt operation. For deviation, the control system also adjusts the tension of the tensioning device based on the degree of deviation. For example, in the case of mild deviation, the tension is increased by 5%; in the case of severe deviation, the tension is increased by 10%. The tension is adjusted using a hydraulic or electric tensioning device to ensure the belt returns to centering. During the adjustment process, the system continuously acquires images of the belt surface to monitor the belt's operating status in real time. If the belt fails to resume normal operation within the preset 30 seconds, the system will issue an alarm, prompting the operator to perform inspection and repairs. This continuous monitoring and dynamic adjustment ensures stable and reliable belt operation. This real-time monitoring and dynamic adjustment of the belt's operating status not only improves production line efficiency but also significantly reduces downtime and repair costs caused by belt failures. For example, after implementing this system on one production line, the belt failure rate decreased by 30% and production efficiency increased by 15%. Furthermore, the precise control of the inverter's output frequency and voltage also results in energy savings. The motor operates under optimal conditions, reducing energy consumption and extending equipment life.

[0063] In step S106, the control system adopts an adaptive control algorithm to automatically adjust the parameters of the PID controller according to the operating conditions of the conveyor, so that the control system can adapt to different conveying distances, material loading amounts and environmental conditions. By optimizing the control strategy, the belt tension and speed fluctuations caused by changes in operating conditions are reduced, ensuring the stable operation of the conveyor in a complex and changeable on-site environment.

[0064] Specifically, real-time conveyor operating status data, including belt speed, belt tension, material load, and other parameters, is acquired as input to the adaptive control algorithm. Based on this acquired operating status data, the adaptive control algorithm determines whether the current conveyor operating conditions, such as conveying distance, material load, and ambient temperature, have changed. If the determination indicates a change in operating conditions, the adaptive control algorithm is triggered to calculate the optimal parameter combination for the PID controller based on pre-set rules or a machine learning model. The calculated PID controller parameters are then distributed to the control system, which adjusts the conveyor's operating status in real time to maintain belt speed and tension within a reasonable range. During this adjustment process, the conveyor's operating status is continuously monitored, and feedback data is obtained to evaluate control effectiveness and optimize the control strategy. Using machine learning algorithms such as neural networks or support vector machines, historical operating data is trained to establish a mapping between conveyor operating conditions and optimal control parameters, forming an adaptive control model. Once the adaptive control model is deployed in the control system, the control system can quickly respond to changes in operating conditions and automatically adjust the PID controller parameters to ensure stable conveyor operation and improve control accuracy and efficiency.

[0065] In this embodiment, real-time conveyor operating status data collection forms the foundation of adaptive control. Taking belt speed as an example, an encoder mounted on the drive roller shaft acquires speed signals in real time, with a typical sampling period of milliseconds and a speed range of 0.5 to 3 meters per second. Tension data is collected using a tension sensor, with a common measurement range of 0 to 5 kilonewtons. Material load capacity can be measured using a load cell, with an accuracy of up to 0.5 percent. Determining operating conditions requires comprehensive consideration of multiple factors. Changes in conveying distance can affect system inertia and resistance characteristics. For example, increasing the conveying distance from 100 meters to 200 meters significantly increases system inertia. Fluctuations in material load capacity can alter system load characteristics. Increasing the load capacity from 50 tons per hour to 100 tons requires corresponding adjustment of control parameters. Ambient temperature significantly impacts equipment performance. A temperature rise from -20°C to 40°C can significantly alter the mechanical characteristics of the equipment. The core of the adaptive control algorithm is the dynamic adjustment of control parameters. Taking a proportional-integral-derivative controller as an example, a machine learning model can establish a relationship between operating conditions and optimal parameters. For example, under light-load conditions, the proportional coefficient can be set to 2.5, the integral time to 0.8 seconds, and the differential time to 0.2 seconds. Under heavy-load conditions, the proportional coefficient needs to be increased to 4.0, and the integral time extended to 1.2 seconds. Control effectiveness is evaluated using multiple metrics. The speed fluctuation must be kept below 2%, the overshoot no more than 5%, and the settling time less than three seconds. The system calculates these metrics in real time to evaluate control effectiveness and optimize the control strategy accordingly. Historical data is typically collected at a one-second interval and stored for up to one year, providing ample samples for machine learning model training. The adaptive control model is built using a multi-layer neural network architecture. The input layer contains operating parameters such as speed and load. The hidden layer is a three-layer structure, each containing ten neurons. The output layer corresponds to the controller parameters. Model training uses the backpropagation algorithm, with a learning rate of 0.01 and 1,000 training rounds. The support vector machine uses a radial basis kernel function with a kernel parameter of 0.1 and a penalty factor of 100. After model deployment, system response speed has been significantly improved. When the working conditions change suddenly, such as a 50% increase in material loading, the traditional fixed parameter controller takes more than five seconds to stabilize. However, with adaptive control, the system can be restored to stability in just two seconds, greatly improving control accuracy and efficiency.

[0066] This embodiment also provides an adaptive variable frequency speed control system for a belt conveyor, comprising:

[0067] The tension control module is used to obtain the belt tension data and transmit the tension data to the control system to determine whether it exceeds the preset tension threshold range. If it exceeds the preset tension threshold range, the control system adjusts the belt tension through the control signal;

[0068] The conveying distance compensation module is used to obtain the current conveying distance data, compare the current conveying distance data with the preset standard conveying distance, obtain the conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value;

[0069] The loading control module is used to obtain the current material loading data, compare the current material loading data with the preset standard loading, obtain the loading deviation value, and adjust the material loading speed according to the loading deviation value;

[0070] The speed control module is used to obtain the current belt speed data, compare the current belt speed data with the preset standard speed, obtain the speed deviation value, and adjust the motor speed according to the speed deviation value;

[0071] The operating status monitoring module is used to monitor the operating status of the belt in real time through machine vision technology to determine whether slippage or deviation occurs. If slippage or deviation occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slippage or deviation.

[0072] Adaptive control module, the control system adopts adaptive control algorithm, calculates the optimal parameter combination of PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination.

[0073] This embodiment further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0074] This embodiment further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0075] This embodiment also provides a computer program product, including a computer program, which implements the steps of the method when executed by a processor.

[0076] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An adaptive variable frequency speed control method for a belt conveyor, characterized in that: The following steps are involved: Acquire belt tension data, transmit the tension data to a control system to determine whether it exceeds a preset tension threshold range, and if so, adjust the belt tension through a control signal; Acquire current conveying distance data, compare the current conveying distance data with a preset standard conveying distance, obtain a conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value; Obtaining current material loading data, comparing the current material loading data with a preset standard loading amount to obtain a loading deviation value, and adjusting the material loading speed according to the loading deviation value; Acquire current belt speed data, compare the current belt speed data with a preset standard speed to obtain a speed deviation value, and adjust the motor speed according to the speed deviation value; The running status of the belt is monitored in real time through machine vision technology to determine whether it is slipping or deviating. If slipping or deviating occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slipping or deviation. Adjust the inverter output and the tensioning force of the tensioning device according to the degree of slippage and deviation, including: Construct a skidding and deviation discrimination model based on support vector machine; Acquire the belt surface image, use image preprocessing technology to denoise and enhance the image; use texture feature extraction algorithm to extract the belt surface texture features and obtain the texture feature vector; Inputting the texture feature vector into a slip and deviation discrimination model to obtain a belt state; adjusting the output of the frequency converter and the tensioning force of the tensioning device according to the belt state; The control system adopts an adaptive control algorithm to calculate the optimal parameter combination of the PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination; Control of belt conveyor includes: The neural network is trained through historical operating data to establish a mapping relationship between conveyor operating conditions and optimal control parameters, and obtain an adaptive control model; Calculate the optimal parameter combination of PID controller through adaptive control model; The belt conveyor is regulated according to the optimal parameter combination.

2. The method according to claim 1, characterized in that Adjusting the belt tension includes: the control system issues an adjustment instruction, and by adjusting the output frequency and voltage amplitude of the inverter, changes the speed and torque of the motor, thereby adjusting the running speed and tension of the belt.

3. The method according to claim 1, characterized in that Adjusting the belt length includes: controlling the extension amount and extension direction of the telescopic mechanism according to the size and positive and negative of the conveying distance deviation value to adjust the belt length and compensate for the belt tension fluctuation caused by the change of the conveying distance.

4. The method according to claim 1, wherein Adjusting the loading speed of the material includes: controlling the feeding speed of the feeding device according to the size of the loading amount deviation value, and controlling the loading amount by adjusting the loading speed of the material.

5. An adaptive variable frequency speed control system for a belt conveyor, characterized in that: include: The tension control module is used to obtain the belt tension data and transmit the tension data to the control system to determine whether it exceeds the preset tension threshold range. If it exceeds the preset tension threshold range, the control system adjusts the belt tension through the control signal; A conveying distance compensation module is used to obtain current conveying distance data, compare the current conveying distance data with a preset standard conveying distance, obtain a conveying distance deviation value, and adjust the belt length according to the conveying distance deviation value; A loading control module is used to obtain current material loading data, compare the current material loading data with a preset standard loading, obtain a loading deviation value, and adjust the material loading speed according to the loading deviation value; A speed control module is used to obtain current belt speed data, compare the current belt speed data with a preset standard speed, obtain a speed deviation value, and adjust the motor speed according to the speed deviation value; The operating status monitoring module is used to monitor the operating status of the belt in real time through machine vision technology to determine whether slippage or deviation occurs. If slippage or deviation occurs, the output of the inverter and the tension of the tensioning device are adjusted according to the degree of slippage or deviation. The adaptive control module adopts an adaptive control algorithm to calculate the optimal parameter combination of the PID controller according to the operating conditions of the conveyor, and regulates the belt conveyor according to the optimal parameter combination.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images